| Name | claude-skills-mcp JSON |
| Version |
1.0.6
JSON |
| download |
| home_page | None |
| Summary | Lightweight MCP proxy for Claude Skills (auto-downloads backend) |
| upload_time | 2025-10-24 01:20:22 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | <3.13,>=3.12 |
| license | Apache-2.0 |
| keywords |
agent
ai
claude
mcp
proxy
skills
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# Claude Skills MCP Frontend
Lightweight MCP proxy for Claude Skills that auto-downloads the heavy backend on demand.
## Overview
This is the frontend component of the Claude Skills MCP system. It's a lightweight proxy (~15 MB) that:
- Starts instantly (<5 seconds)
- Auto-downloads the backend when first needed
- Acts as MCP server (stdio) for Cursor
- Acts as MCP client (HTTP) for the backend
- Returns tool schemas immediately (no backend wait needed)
## Installation
```bash
# Via uvx (recommended for Cursor)
uvx claude-skills-mcp
# Via uv tool (persistent install)
uv tool install claude-skills-mcp
# Via pip
pip install claude-skills-mcp
```
## Usage with Cursor
Add to your Cursor MCP settings (`~/.cursor/mcp.json`):
```json
{
"mcpServers": {
"claude-skills": {
"command": "uvx",
"args": ["claude-skills-mcp"]
}
}
}
```
Restart Cursor and the skills will be available!
### First Run Behavior
On first run, the frontend will:
1. Start immediately (~5 seconds) ✅ **Cursor timeout satisfied!**
2. Return tool schemas to Cursor (instant)
3. Download backend in background (~250 MB, 60-120 seconds)
4. When you first use a tool, you'll see "Loading backend..."
5. Once backend ready, all tools work normally
**Subsequent runs**: Fast! Backend is already installed.
## Configuration
The frontend forwards all arguments to the backend:
```bash
# Custom configuration
uvx claude-skills-mcp --config my-config.json
# Verbose logging
uvx claude-skills-mcp --verbose
# Custom backend port (advanced)
uvx claude-skills-mcp --port 9000
```
## Remote Backend (Future)
```bash
# Connect to hosted backend instead of local
uvx claude-skills-mcp --remote https://skills.k-dense.ai/mcp
```
**Note**: Remote backend support coming in v1.1.0
## How It Works
```
Cursor → Frontend (stdio, ~15 MB)
↓
list_tools() → Returns hardcoded schemas INSTANTLY ✅
↓
[Backend downloads in background...]
↓
call_tool() → Proxies to Backend (HTTP)
↓
Backend (HTTP, ~250 MB) → Performs actual search
```
This architecture solves the Cursor timeout problem by separating:
- **Fast startup** (frontend, minimal dependencies)
- **Heavy processing** (backend, downloads async)
## Dependencies
Frontend only requires:
- `mcp>=1.0.0` (~5 MB)
- `httpx>=0.24.0` (~5 MB)
**Total**: ~15 MB (downloads in <10 seconds)
The backend (`claude-skills-mcp-backend`) is auto-installed on first use.
## Troubleshooting
### "Backend not ready" message
On first run, you'll see this message for 30-120 seconds while the backend downloads. This is normal and only happens once.
### Backend installation fails
Check:
1. Internet connection
2. Disk space (~500 MB free needed)
3. Python 3.12 installed
### Tools not working
Run with verbose logging:
```bash
uvx claude-skills-mcp --verbose
```
Check logs in stderr for backend status.
## Development
```bash
# Clone the monorepo
git clone https://github.com/K-Dense-AI/claude-skills-mcp.git
cd claude-skills-mcp/packages/frontend
# Install in development mode
uv pip install -e ".[test]"
# Run tests
uv run pytest tests/
```
## Related Packages
- **claude-skills-mcp-backend** (Backend): Heavy server with vector search
- **Main Repository**: https://github.com/K-Dense-AI/claude-skills-mcp
## License
Apache License 2.0
Copyright 2025 K-Dense AI (https://k-dense.ai)
Raw data
{
"_id": null,
"home_page": null,
"name": "claude-skills-mcp",
"maintainer": null,
"docs_url": null,
"requires_python": "<3.13,>=3.12",
"maintainer_email": "K-Dense AI <orion.li@k-dense.ai>",
"keywords": "agent, ai, claude, mcp, proxy, skills",
"author": null,
"author_email": "K-Dense AI <orion.li@k-dense.ai>",
"download_url": "https://files.pythonhosted.org/packages/7e/fb/48f91721f8371bc999f672c893d0fa979944f340eba6d42bbef967e7c2c1/claude_skills_mcp-1.0.6.tar.gz",
"platform": null,
"description": "# Claude Skills MCP Frontend\n\nLightweight MCP proxy for Claude Skills that auto-downloads the heavy backend on demand.\n\n## Overview\n\nThis is the frontend component of the Claude Skills MCP system. It's a lightweight proxy (~15 MB) that:\n- Starts instantly (<5 seconds)\n- Auto-downloads the backend when first needed\n- Acts as MCP server (stdio) for Cursor\n- Acts as MCP client (HTTP) for the backend\n- Returns tool schemas immediately (no backend wait needed)\n\n## Installation\n\n```bash\n# Via uvx (recommended for Cursor)\nuvx claude-skills-mcp\n\n# Via uv tool (persistent install)\nuv tool install claude-skills-mcp\n\n# Via pip\npip install claude-skills-mcp\n```\n\n## Usage with Cursor\n\nAdd to your Cursor MCP settings (`~/.cursor/mcp.json`):\n\n```json\n{\n \"mcpServers\": {\n \"claude-skills\": {\n \"command\": \"uvx\",\n \"args\": [\"claude-skills-mcp\"]\n }\n }\n}\n```\n\nRestart Cursor and the skills will be available!\n\n### First Run Behavior\n\nOn first run, the frontend will:\n1. Start immediately (~5 seconds) \u2705 **Cursor timeout satisfied!**\n2. Return tool schemas to Cursor (instant)\n3. Download backend in background (~250 MB, 60-120 seconds)\n4. When you first use a tool, you'll see \"Loading backend...\"\n5. Once backend ready, all tools work normally\n\n**Subsequent runs**: Fast! Backend is already installed.\n\n## Configuration\n\nThe frontend forwards all arguments to the backend:\n\n```bash\n# Custom configuration\nuvx claude-skills-mcp --config my-config.json\n\n# Verbose logging\nuvx claude-skills-mcp --verbose\n\n# Custom backend port (advanced)\nuvx claude-skills-mcp --port 9000\n```\n\n## Remote Backend (Future)\n\n```bash\n# Connect to hosted backend instead of local\nuvx claude-skills-mcp --remote https://skills.k-dense.ai/mcp\n```\n\n**Note**: Remote backend support coming in v1.1.0\n\n## How It Works\n\n```\nCursor \u2192 Frontend (stdio, ~15 MB)\n \u2193\n list_tools() \u2192 Returns hardcoded schemas INSTANTLY \u2705\n \u2193\n [Backend downloads in background...]\n \u2193\n call_tool() \u2192 Proxies to Backend (HTTP)\n \u2193\n Backend (HTTP, ~250 MB) \u2192 Performs actual search\n```\n\nThis architecture solves the Cursor timeout problem by separating:\n- **Fast startup** (frontend, minimal dependencies)\n- **Heavy processing** (backend, downloads async)\n\n## Dependencies\n\nFrontend only requires:\n- `mcp>=1.0.0` (~5 MB)\n- `httpx>=0.24.0` (~5 MB)\n\n**Total**: ~15 MB (downloads in <10 seconds)\n\nThe backend (`claude-skills-mcp-backend`) is auto-installed on first use.\n\n## Troubleshooting\n\n### \"Backend not ready\" message\n\nOn first run, you'll see this message for 30-120 seconds while the backend downloads. This is normal and only happens once.\n\n### Backend installation fails\n\nCheck:\n1. Internet connection\n2. Disk space (~500 MB free needed)\n3. Python 3.12 installed\n\n### Tools not working\n\nRun with verbose logging:\n```bash\nuvx claude-skills-mcp --verbose\n```\n\nCheck logs in stderr for backend status.\n\n## Development\n\n```bash\n# Clone the monorepo\ngit clone https://github.com/K-Dense-AI/claude-skills-mcp.git\ncd claude-skills-mcp/packages/frontend\n\n# Install in development mode\nuv pip install -e \".[test]\"\n\n# Run tests\nuv run pytest tests/\n```\n\n## Related Packages\n\n- **claude-skills-mcp-backend** (Backend): Heavy server with vector search\n- **Main Repository**: https://github.com/K-Dense-AI/claude-skills-mcp\n\n## License\n\nApache License 2.0\n\nCopyright 2025 K-Dense AI (https://k-dense.ai)\n\n",
"bugtrack_url": null,
"license": "Apache-2.0",
"summary": "Lightweight MCP proxy for Claude Skills (auto-downloads backend)",
"version": "1.0.6",
"project_urls": {
"Backend": "https://pypi.org/project/claude-skills-mcp-backend/",
"Bug Tracker": "https://github.com/K-Dense-AI/claude-skills-mcp/issues",
"Documentation": "https://github.com/K-Dense-AI/claude-skills-mcp/blob/main/README.md",
"Homepage": "https://github.com/K-Dense-AI/claude-skills-mcp",
"Repository": "https://github.com/K-Dense-AI/claude-skills-mcp"
},
"split_keywords": [
"agent",
" ai",
" claude",
" mcp",
" proxy",
" skills"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "24cfedb94a574d79fafed971190abe3400ad22024248faff103730909d063b55",
"md5": "a200a0e39f0eea2ff049efa202a99a18",
"sha256": "2846d349391af4094d59fb97cd1c2ec860ed986e73c70c2724f1a38bd1922c25"
},
"downloads": -1,
"filename": "claude_skills_mcp-1.0.6-py3-none-any.whl",
"has_sig": false,
"md5_digest": "a200a0e39f0eea2ff049efa202a99a18",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<3.13,>=3.12",
"size": 12618,
"upload_time": "2025-10-24T01:20:21",
"upload_time_iso_8601": "2025-10-24T01:20:21.446719Z",
"url": "https://files.pythonhosted.org/packages/24/cf/edb94a574d79fafed971190abe3400ad22024248faff103730909d063b55/claude_skills_mcp-1.0.6-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "7efb48f91721f8371bc999f672c893d0fa979944f340eba6d42bbef967e7c2c1",
"md5": "b98998cd86f04b6fad0d6b37b7edef1a",
"sha256": "80bb2bdfb03c4fed69878ae3dfea20beeb10ae9b3e633a3cd69c18facc063884"
},
"downloads": -1,
"filename": "claude_skills_mcp-1.0.6.tar.gz",
"has_sig": false,
"md5_digest": "b98998cd86f04b6fad0d6b37b7edef1a",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<3.13,>=3.12",
"size": 23056,
"upload_time": "2025-10-24T01:20:22",
"upload_time_iso_8601": "2025-10-24T01:20:22.694372Z",
"url": "https://files.pythonhosted.org/packages/7e/fb/48f91721f8371bc999f672c893d0fa979944f340eba6d42bbef967e7c2c1/claude_skills_mcp-1.0.6.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-10-24 01:20:22",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "K-Dense-AI",
"github_project": "claude-skills-mcp",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "claude-skills-mcp"
}
